Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
The embodiment of the application a part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
Member's every other embodiment obtained without making creative work, all should belong to the model of the application protection
It encloses.
It should be noted that the description and claims of this application and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to embodiments herein described herein.In addition, term " includes " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing a series of steps or units
Process, method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include without clear
Other step or units listing to Chu or intrinsic for these process, methods, product or equipment.
In this application, term " on ", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outside",
" in ", "vertical", "horizontal", " transverse direction ", the orientation or positional relationship of the instructions such as " longitudinal direction " be orientation based on the figure or
Positional relationship.These terms are not intended to limit indicated dress primarily to better describe the application and embodiment
Set, element or component must have particular orientation, or constructed and operated with particular orientation.
Also, above-mentioned part term is other than it can be used to indicate that orientation or positional relationship, it is also possible to for indicating it
His meaning, such as term " on " also are likely used for indicating certain relations of dependence or connection relationship in some cases.For ability
For the those of ordinary skill of domain, the concrete meaning of these terms in this application can be understood as the case may be.
In addition, term " installation ", " setting ", " being equipped with ", " connection ", " connected ", " socket " shall be understood in a broad sense.For example,
It may be a fixed connection, be detachably connected or monolithic construction;It can be mechanical connection, or electrical connection;It can be direct phase
It even, or indirectly connected through an intermediary, or is two connections internal between device, element or component.
For those of ordinary skills, the concrete meaning of above-mentioned term in this application can be understood as the case may be.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
In the recognition methods for broadcasting content of the application, comprising: receive the first identification request of first content;It determines
First broadcasting content of the first content;And first broadcasting content is executed according to the first identification request default
Content recognition operation.
Through the present processes for programme content side, can accurately it be carried out in any position with spectators mutual
It is dynamic, such as synchronous answer, ballot, prize drawing, push etc., it also may be implemented to see the interaction between the spectators of program simultaneously, for example chat
It, guess etc..It, can be with since the content and playback progress that user is watched can be understood in real time for the application of mobile terminal
Push the stronger content of correlation or service.
As shown in Figure 1, this method includes the following steps, namely S102 to step S106:
Step S102 receives the first identification request of first content,
For identifying the service request of service as broadcasting content, broadcasting content identification service refers to for first identification request,
The audio-video frequency content or audio-video command signal that locating environment plays can be identified by the service internet device.
When the identification for receiving first content is requested, can be behind the front end of application program or application program
End.
Specifically, broadcasting content identification service refers to identification content and optionally identifies the ability of playback progress.
Specifically, what broadcasting content identification service can identify that user views or listens to is what watches content;And into one
Step ground spectators see or have heard where this program i.e. viewing progress.
Step S104 determines the first broadcasting content of the first content,
First broadcasting content is used for as the service content based on broadcasting content, and the service content based on broadcasting content is
Refer to, identifies that the recognition capability that service provides realizes various applications dependent on broadcasting content.For example, in can be and watching or listen to
The information of appearance pushes;Watch or listen to simultaneously the interaction of the spectators of identical content.
Service based on broadcasting content is needed based on identification broadcasting content and playback progress to mobile subscriber or third
Side provides value-added service,
In some embodiments, the first broadcasting content of the first content can be, while watch the institute of certain program
There are chatroom, the barrage of spectators' participation.At this point, the progress of chat or barrage is consistent with the process that program plays.
In some embodiments, the first broadcasting content of the first content can be, and go wrong in answer class program
When, mobile phone simultaneous ejection problem is answered in mobile terminal for spectators and closes answer before player answers, and player answers it
Correct option is shown in mobile terminal afterwards.
In some embodiments, the first broadcasting content of the first content can be, when some content occurs in program
When, mobile terminal pushes the more detailed content and Action Links (Call for Action) about this content, such as good
Guest's information, product purchase link, ballot, selection etc..
In some embodiments, the first broadcasting content of the first content can be, view or listen to program when
It waits, relevant information is automatically saved to mobile terminal, plays the function of account, check afterwards.For example drive to listen to the radio programme, it is looked into after getting off
Ask relevant information.
In some embodiments, the first broadcasting content of the first content can be, and the advertisement is pushed around billboard
Action Links to mobile device near billboard.
In some embodiments, the first broadcasting content of the first content can be, and market sends surrounding businessman and gives a discount
Mobile device in information, discount coupon to market.
In some embodiments, the first broadcasting content of the first content can be, and application program is current according to user
The content of viewing pushes the stronger content of correlation by intelligent recommendation algorithm, for example microblogging is currently viewing user or listens to
Content as a recommendation factor, recommend relevant information inside information flow.
In some embodiments, the first broadcasting content of the first content can be, small when viewing game is broadcast live
Screen cooperation shows the game information of more players.
In some embodiments, the first broadcasting content of the first content can be, and increases and adds audio to films and television programs
Watermark.
Step S106 executes preset content identification operation to first broadcasting content according to the first identification request.
The service content based on broadcasting content is executed according to the service request of above-mentioned broadcasting content identification service default
Content recognition mixing operation, since different content identification methods is applicable to different scenes, so needing for different
Identification request executes preset content identification operation.For example, synchronous answer need to identify using watermark or with content playing platform
Form cooperation;For another example, fingerprint recognition etc. can be used in general content push.
In addition, another aspect, according to the service request of above-mentioned broadcasting content identification service to based on broadcasting content
Service content execute preset content identification mixing operation and can guarantee the validity and universality of content service.For example, user
The analysis for providing some specific program or user behavior habit can be with the knot of cross validation watermark identification and fingerprint recognition
Fruit;For another example, fingerprint recognition can assist watermark to identify the identification for first carrying out low precision, to reduce the length of fingerprint recognition code
Deng.Optimal knowledge can be only achieved for different application scenarios using the method for multiple technologies fusion for content identification service
Other effect.
It can be seen from the above description that the application realizes following technical effect:
In the embodiment of the present application, by the way of receiving the first identification request of first content, pass through determination described the
First broadcasting content of one content has reached and has executed preset content to first broadcasting content according to the first identification request
Identify the purpose of operation, to realize broadcasting content fusion recognition, recognition result has the technology of real-time and accuracy effect
Fruit, and then solve the technical problem poor for broadcasting content recognition effect.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in Fig. 2, determining the of the first content
One broadcasting content includes:
Step S202 judges whether the broadcasting content in first content is to collect audio/video information;
Judge whether the broadcasting content in first content is the audio/video information that can be collected.
Specifically, the audio/video information that can be collected can acquire, by adding watermark in video or audio
Label, the information of the unique identifier containing this video and the timestamp of playback progress in label.
Specifically, it the audio/video information that can collect or acquires, passes through video or the fingerprint characteristic of audio
The fingerprint characteristic data library collected in advance compares, to identify audio-video frequency content.Main attention, for fingerprint label
The required time is linear elongated with the content increase for including in database when carrying out fingerprint recognition.Typically, for
Data no more than 100, identification duration are also required to more than ten seconds.
Step S204, if it is determined that the broadcasting content in first content is to collect audio/video information, it is determined that the first view
Audio broadcasting content;
It can be used as collectable audio/video information if it is the broadcasting content for meeting above-mentioned fingerprint or audio conditions.
It should be noted that needing to rely in pretreatment when carrying out watermark identification to the broadcasting content in first content
Hold, while watermark identifies that high-precision synchronization is that second grade is synchronous, and universality is good.Fingerprint is being carried out to the broadcasting content in first content
When identification, dependency need collects all possible program fingerprint characteristics, while the high-precision synchronization of fingerprint recognition is at least more than ten seconds, and
Universality is good.Therefore, it usually needs accuracy content recognition is needed when judging using watermark identification or audio identification.
Executing preset content identification operation to first broadcasting content according to the first identification request includes:
Step S206 according to the watermark label in the first identification request first video and audio broadcasting content of identification or refers to
Line label;
Specifically, watermark label can usually be realized using with code generator, and watermark addition is added by watermark
Algorithm is realized.Usual watermark addition, which will meet, lossless not to be influenced the effect of audio-video.
In addition, watermark addition does not increase file size.For example it if dramatically increasing file size, will affect according to original
The performance of the Transmission system of size design.It also needs to meet anti-rotation for the background process and Transmission system that need transcoding
Code, i.e., watermark will not lose after transcoding.
Preferably, if it is video watermark, mobile device identifies the watermark label in video by camera;If it is sound
Sound watermark, mobile or non-mobile device identify the watermark label in screen by microphone radio reception.In addition, comparison video water
Print, audio frequency watermark does not need user and lifts mobile device alignment screen, therefore has better availability and universality.Identification
Time delay is determined by the length of label, can usually accomplish second grade delay.
There are two types of the modes of audio frequency watermark addition.The first is time except the 20Hz-20KHz range for adding auditory perceptual
Sound wave or supersonic band, if necessary to which audio to be carried out to the scene of transcoding, then the watermark that may be added may be deleted.The
Two kinds are added in the band limits of 20Hz-20KHz, will not the dropped audio watermark in transcoding process;But it needs to avoid
Any influence is generated to existing sound effect.
As preferred in the present embodiment, in the embodiment of the present application by the way of orthogonal spreading code, width is diffused to
Frequent section reduces the energy density of watermark, greatly enhances and resists narrow frequency interference performance.
Specifically, include: in the addition watermark stage
S1. audio file is carried out the conversion of real domain to frequency domain;
S2. PN sequence is generated according to seed random noise (PN) sequence;
S3. bit sequence and PN sequence to be added is needed to generate the PN sequence that can represent bit sequence;
S4. watermark is added in frequency domain;
S5. the audio file of frequency domain is converted back into time domain.
Include: in the parsing watermark stage
S6. the audio file with watermark is subjected to the conversion of time domain to frequency domain;
S7. it obtains representing bit by calculating and comparing correlation correlation values using same PN sequence
The PN sequence of sequence simultaneously obtains original bit sequence.
Due to the mode of orthogonal spreading code, adaptive coding used to time domain, it is automatic to avoid saturation or off beat period
Coding.Saturation or off beat period, timestamp coded system can be avoided automatically, and added in other times section and encoded and increase
Time offset.
Preferably, it using redundancy encoding, improves fault-tolerance and realizes antinoise and coding distortion.
Preferably, using the multi-layer coding mode of hierarchical, code multiplexing and large capacity are realized.
Preferably, stage coding is used in S2 and S3, improves search efficiency, support section identification.
Step S208 determines broadcasting content and playback progress according to the watermark label or fingerprint label.
It the unique identifier containing this video and is broadcast by adding watermark label in video or audio, in label
The information of the timestamp of degree of putting into, thus by watermark label or fingerprint label can determine broadcasting content and play into
Degree.
First judge whether broadcasting content is the audio/video information that can be collected, if it can, being separated into two parts.The
A part checks whether there is watermark information, then starts watermark identification;Second part enters fingerprint recognition, if current identification request
Requirement of real-time can be met by fingerprint recognition, then start fingerprint recognition.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 3, determining the of the first content
One broadcasting content includes:
Step S302, judges whether the broadcasting content in first content for user provides audio/video information;
User provides audio/video information and refers to, watches or listens to the spectators of image and sound program actively by mobile device offer
Audio-video frequency content.For programme televised live, using can probably judge institute's playback progress;For non-programme televised live, using only
It can know that the content that user is watched or listened to.
Step S304, if it is determined that the broadcasting content in first content provides audio/video information for user, it is determined that first
Playing platform broadcasting content;
If it is determined that the broadcasting content in first content provides audio/video information for user, it can determine that playing platform is broadcast
The content put.The content that playing platform plays can be, the programme content that user is viewed or listened to, and can usually use
Mobile device directly or indirectly obtains the broadcasting content of playing platform.For example, internet video website, having a TV
Set-top box, smart television, OTT box etc..
Executing preset content identification operation to first broadcasting content according to the first identification request includes:
Step S306, according to it is described first identification request identification the first playing platform broadcasting content in broadcasting content and
Playback progress.
According to the specific broadcasting content in different identification request the first playing platform broadcasting contents of identification and play into
Degree.The program that playing platform collection can be identified by plays situation, such as the case where TV station's programme televised live.In addition, if
The case where directly cooperating with playing platform, user's request program can be obtained.Pass through platform development interface in the first playing platform
The playback progress of broadcasting content can be obtained.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 4, determining the of the first content
One broadcasting content includes:
Step S402 judges whether the broadcasting content in first content is user's Habit Preference audio/video information;
Analysis user behavior, which can be, views or listens to behavioural habits according to the daily of user, and prediction user is currently seen
The content seen or listened to.
Step S404, if it is determined that the broadcasting content in first content is user's Habit Preference audio/video information, it is determined that
First preference broadcasting content;
If it is determined that the broadcasting content in first content is user's Habit Preference audio/video information, it can determine that user's is inclined
Good broadcasting content, for example, the every weekly assembly of user watches certain grade of variety live streaming in the set time;For another example, what user drove daily is upper
The next time can listen to fixed radio station.
Executing preset content identification operation to first broadcasting content according to the first identification request includes:
Step S406, according to the broadcasting content in the first identification request first preference broadcasting content of identification.
According to the first identification request identification, obtained broadcasting content recognition result is mainly used to cross-check.
For example, fingerprint recognition and watermark identification can do cross validation under the not high scene of requirement of real-time;Work as watermark
When the result of identification and the conventional behavior of user have dramatically different, watermark can be allowed to identify that the identification that tries again is done and confirmed.
According to the embodiment of the present application, as preferred in the present embodiment, as shown in figure 5, being requested according to first identification
Executing preset content identification operation to first broadcasting content includes:
Step S502 is required according to the first identification request judgement identification;
Step S504 requires configuration to execute preset content identification operation according to the identification;
The identification requires to include at least: identifying or accurately identifies in real time, furthermore, it is possible to require identification to carry out weight tax
Value.
Identification generallys use the broadcasting content in watermark identification or playing platform broadcasting content in real time.
It accurately identifies in the broadcasting generallyd use in watermark identification and fingerprint recognition and combination playing platform broadcasting content
Hold.
For example, watermark can be allowed to identify when the result of watermark identification and the conventional behavior of user have dramatically different
The identification that tries again, which is done, to be confirmed.
For another example, if platform play program arrangement may Iterim Change or fingerprint recognition be also possible to go out
Mistake, playing platform announce played data and fingerprint recognition it is different, then can require fingerprint recognition try again identification etc..
The preset content identification operation includes at least: crosscheck or error correction verifying.
Crosscheck refers to according to the broadcasting content in the first identification request first preference broadcasting content of identification.
Error correction verifying refer to according to it is described first identification request identification the first video and audio broadcasting content in watermark label or
Person's fingerprint label.
In above-mentioned steps, the requirements selection such as real-time, accuracy for being requested according to identification recognition methods appropriate is simultaneously real
Recognition result is exported after existing cross validation, error correction, completes the function of broadcasting content identification service.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
According to the embodiment of the present application, additionally provide a kind of for implementing being used for for the above-mentioned recognition methods for broadcasting content
The identification device of broadcasting content, as shown in fig. 6, the device includes:
Receiving module 10, for receiving the first identification request of first content, wherein the first identification request is for making
For the service request of broadcasting content identification service;
Service request of the first identification request for being serviced as broadcasting content identification in the receiving module 10 of the present embodiment,
Broadcasting content identification service refers to, can be identified by the service internet device locating environment broadcasting audio-video frequency content or
It is audio-video command signal.
When the identification for receiving first content is requested, can be behind the front end of application program or application program
End.
Specifically, broadcasting content identification service refers to identification content and optionally identifies the ability of playback progress.
Specifically, what broadcasting content identification service can identify that user views or listens to is what watches content;And into one
Step ground spectators see or have heard where this program i.e. viewing progress.
Determining module 20, for determining the first broadcasting content of the first content, wherein first broadcasting content is used
In as the service content based on broadcasting content;And
The first broadcasting content is used to be based on as the service content based on broadcasting content in the determining module 20 of the present embodiment
The service content of broadcasting content refers to, identifies that the recognition capability that service provides realizes various applications dependent on broadcasting content.For example,
It can be the information push for watching or listening to content;Watch or listen to simultaneously the interaction of the spectators of identical content.
Service based on broadcasting content is needed based on identification broadcasting content and playback progress to mobile subscriber or third
Side provides value-added service,
In some embodiments, the first broadcasting content of the first content can be, while watch the institute of certain program
There are chatroom, the barrage of spectators' participation.At this point, the progress of chat or barrage is consistent with the process that program plays.
In some embodiments, the first broadcasting content of the first content can be, and go wrong in answer class program
When, mobile phone simultaneous ejection problem is answered in mobile terminal for spectators and closes answer before player answers, and player answers it
Correct option is shown in mobile terminal afterwards.
In some embodiments, the first broadcasting content of the first content can be, when some content occurs in program
When, mobile terminal pushes the more detailed content and Action Links (Call for Action) about this content, such as good
Guest's information, product purchase link, ballot, selection etc..
In some embodiments, the first broadcasting content of the first content can be, view or listen to program when
It waits, relevant information is automatically saved to mobile terminal, plays the function of account, check afterwards.For example drive to listen to the radio programme, it is looked into after getting off
Ask relevant information.
In some embodiments, the first broadcasting content of the first content can be, and the advertisement is pushed around billboard
Action Links to mobile device near billboard.
In some embodiments, the first broadcasting content of the first content can be, and market sends surrounding businessman and gives a discount
Mobile device in information, discount coupon to market.
In some embodiments, the first broadcasting content of the first content can be, and application program is current according to user
The content of viewing pushes the stronger content of correlation by intelligent recommendation algorithm, for example microblogging is currently viewing user or listens to
Content as a recommendation factor, recommend relevant information inside information flow.
In some embodiments, the first broadcasting content of the first content can be, small when viewing game is broadcast live
Screen cooperation shows the game information of more players.
In some embodiments, the first broadcasting content of the first content can be, and increases and adds audio to films and television programs
Watermark.
Fusion recognition module 30, for executing preset content to first broadcasting content according to the first identification request
Identification operation.
According to the service request of above-mentioned broadcasting content identification service to being based in the fusion recognition module 30 of the present embodiment
The service content of broadcasting content executes preset content and identifies mixing operation, since different content identification methods is applicable to difference
Scene, so needing to execute preset content identification operation for different identification requests.For example, synchronous answer is needed using water
Print identification forms cooperation with content playing platform;For another example, fingerprint recognition etc. can be used in general content push.
In addition, another aspect, according to the service request of above-mentioned broadcasting content identification service to based on broadcasting content
Service content execute preset content identification mixing operation and can guarantee the validity and universality of content service.For example, user
The analysis for providing some specific program or user behavior habit can be with the knot of cross validation watermark identification and fingerprint recognition
Fruit;For another example, fingerprint recognition can assist watermark to identify the identification for first carrying out low precision, to reduce the length of fingerprint recognition code
Deng.Optimal knowledge can be only achieved for different application scenarios using the method for multiple technologies fusion for content identification service
Other effect.
According to the embodiment of the present application, a kind of identification device for broadcasting content is provided, as shown in fig. 7, the determination
Module 20 includes: the first judging unit 201, the first determination unit 202, and the fusion recognition module 30 includes: the first identification list
First 301, second determination unit 302,
First judging unit 201, for judging whether the broadcasting content in first content is to collect audio/video information;
Judge whether the broadcasting content in first content is the sound that can be collected in first judging unit 201 of the present embodiment
Video information.
Specifically, the audio/video information that can be collected can acquire, by adding watermark in video or audio
Label, the information of the unique identifier containing this video and the timestamp of playback progress in label.
Specifically, it the audio/video information that can collect or acquires, passes through video or the fingerprint characteristic of audio
The fingerprint characteristic data library collected in advance compares, to identify audio-video frequency content.Main attention, for fingerprint label
The required time is linear elongated with the content increase for including in database when carrying out fingerprint recognition.Typically, for
Data no more than 100, identification duration are also required to more than ten seconds.
First determination unit 202 when for judging the broadcasting content in first content to collect audio/video information, determines
First video and audio broadcasting content;
It can if it is the broadcasting content for meeting above-mentioned fingerprint or audio conditions in first determination unit 202 of the present embodiment
Using as collectable audio/video information.
It should be noted that needing to rely in pretreatment when carrying out watermark identification to the broadcasting content in first content
Hold, while watermark identifies that high-precision synchronization is that second grade is synchronous, and universality is good.Fingerprint is being carried out to the broadcasting content in first content
When identification, dependency need collects all possible program fingerprint characteristics, while the high-precision synchronization of fingerprint recognition is at least more than ten seconds, and
Universality is good.Therefore, it usually needs accuracy content recognition is needed when judging using watermark identification or audio identification.
First recognition unit 301, for according to the water in the first identification request first video and audio broadcasting content of identification
Marking label or fingerprint label;
In first recognition unit 301 of the present embodiment specifically, watermark label usually can using with code generator come
It realizes, watermark addition is realized by the algorithm that watermark is added.Usual watermark addition will meet lossless i.e. to the effect of audio-video
Do not influence.
In addition, watermark addition does not increase file size.For example it if dramatically increasing file size, will affect according to original
The performance of the Transmission system of size design.It also needs to meet anti-rotation for the background process and Transmission system that need transcoding
Code, i.e., watermark will not lose after transcoding.
Preferably, if it is video watermark, mobile device identifies the watermark label in video by camera;If it is sound
Sound watermark, mobile or non-mobile device identify the watermark label in screen by microphone radio reception.In addition, comparison video water
Print, audio frequency watermark does not need user and lifts mobile device alignment screen, therefore has better availability and universality.Identification
Time delay is determined by the length of label, can usually accomplish second grade delay.
There are two types of the modes of audio frequency watermark addition.The first is time except the 20Hz-20KHz range for adding auditory perceptual
Sound wave or supersonic band, if necessary to which audio to be carried out to the scene of transcoding, then the watermark that may be added may be deleted.The
Two kinds are added in the band limits of 20Hz-20KHz, will not the dropped audio watermark in transcoding process;But it needs to avoid
Any influence is generated to existing sound effect.
As preferred in the present embodiment, in the embodiment of the present application by the way of orthogonal spreading code, width is diffused to
Frequent section reduces the energy density of watermark, greatly enhances and resists narrow frequency interference performance.
Specifically, include: in the addition watermark stage
S1. audio file is carried out the conversion of real domain to frequency domain;
S2. PN sequence is generated according to seed random noise (PN) sequence;
S3. bit sequence and PN sequence to be added is needed to generate the PN sequence that can represent bit sequence;
S4. watermark is added in frequency domain;
S5. the audio file of frequency domain is converted back into time domain.
Include: in the parsing watermark stage
S6. the audio file with watermark is subjected to the conversion of time domain to frequency domain;
S7. it obtains representing bit by calculating and comparing correlation correlation values using same PN sequence
The PN sequence of sequence simultaneously obtains original bit sequence.
Due to the mode of orthogonal spreading code, adaptive coding used to time domain, it is automatic to avoid saturation or off beat period
Coding.Saturation or off beat period, timestamp coded system can be avoided automatically, and added in other times section and encoded and increase
Time offset.
Preferably, it using redundancy encoding, improves fault-tolerance and realizes antinoise and coding distortion.
Preferably, using the multi-layer coding mode of hierarchical, code multiplexing and large capacity are realized.
Preferably, stage coding is used in S2 and S3, improves search efficiency, support section identification.
Second determination unit 302, for determining broadcasting content and broadcasting according to the watermark label or fingerprint label
Progress.
By adding watermark label in video or audio in second determination unit 302 of the present embodiment, contain in label
There is the information of the unique identifier of this video and the timestamp of playback progress, to pass through watermark label or fingerprint label
It can determine broadcasting content and playback progress.
First judge whether broadcasting content is the audio/video information that can be collected, if it can, being separated into two parts.The
A part checks whether there is watermark information, then starts watermark identification;Second part enters fingerprint recognition, if current identification request
Requirement of real-time can be met by fingerprint recognition, then start fingerprint recognition.
According to the embodiment of the present application, a kind of identification device for broadcasting content is provided, as shown in figure 8, the determination
Module 20 includes: the second determination unit 203, the second determination unit 204, third determination unit 205, the fusion recognition module 30
It include: the second recognition unit 303,
Second judgment unit 203, for judging whether the broadcasting content in first content is user's Habit Preference audio-video
Information;
User provides audio/video information and refers in the second judgment unit 203 of the present embodiment, watches or listens to image and sound program
Spectators actively pass through mobile device provide audio-video frequency content.For programme televised live, using can probably judge to be broadcast
Degree of putting into;For non-programme televised live, application can only know the content that user is watched or listened to.
Third determination unit 204, for judging the broadcasting content in first content for user's Habit Preference audio/video information
When, it is determined that the first preference broadcasting content;
If it is determined that the broadcasting content in first content provides sound view for user in the third determination unit 204 of the present embodiment
Frequency information can determine the content that playing platform plays.The content that playing platform plays can be, and user watches or receives
The programme content listened, and the broadcasting content of playing platform usually can be directly or indirectly obtained using mobile device.Than
Such as, internet video website, the set-top box for having a TV, smart television, OTT box etc..
Second recognition unit 303, for according to the broadcasting in the first identification request first preference broadcasting content of identification
Content.
According to different identification request the first playing platform broadcasting contents of identification in second recognition unit 303 of the present embodiment
In specific broadcasting content and playback progress.The program that playing platform collection can be identified by plays situation, such as TV
The case where platform programme televised live.In addition, if the case where directly cooperating with playing platform, user's request program can be obtained.Pass through
Platform development interface can obtain the playback progress of broadcasting content in first playing platform.
According to the embodiment of the present application, a kind of identification device for broadcasting content is provided, as shown in figure 9, the determination
Module 20 includes: the 4th determination unit 205, third judging unit 206, and the fusion recognition module 30 includes: the 5th determining single
First 304, third recognition unit 305,
4th determination unit 205, for determining that the first broadcasting content of the first content includes:
User behavior is analyzed in 4th determination unit 205 of the present embodiment can be according to the daily viewing of user or receipts
Behavioural habits are listened, predict the content that user is currently watched or listens to.
Third judging unit 206, for judging whether the broadcasting content in first content is user's Habit Preference audio-video
Information;
If it is determined that the broadcasting content in first content is user's Habit Preference in the third judging unit 206 of the present embodiment
Audio/video information can determine the preference broadcasting content of user, for example, the every weekly assembly of user watches that certain grade of variety is straight in the set time
It broadcasts;For another example, the time on and off duty that user drives daily can listen to fixed radio station.
5th determination unit 304, for judging the broadcasting content in first content for user's Habit Preference audio/video information
When, it is determined that the first preference broadcasting content;
According to the first identification request identification in 5th determination unit 304 of the present embodiment, obtained broadcasting content is known
Other result is mainly used to cross-check.
For example, fingerprint recognition and watermark identification can do cross validation under the not high scene of requirement of real-time;Work as watermark
When the result of identification and the conventional behavior of user have dramatically different, watermark can be allowed to identify that the identification that tries again is done and confirmed.
Third recognition unit 305, for according to the broadcasting in the first identification request first preference broadcasting content of identification
Content.
According to the embodiment of the present application, a kind of identification device for broadcasting content, as shown in Figure 10, the fusion are provided
Identification module 30 includes:
Identification requires judging unit 306, for being required according to the first identification request judgement identification;
Integrated unit 307 is configured, for requiring configuration to execute preset content identification operation according to the identification;Wherein, institute
State identification to require to include at least: identifying or accurately identify in real time, preset content identification operation includes at least: cross-checking or
Error correction verifying.
The third recognition unit 305 of the present embodiment, identification require institute in judging unit 306 and configuration integrated unit 307
It states identification to require to include at least: identifying or accurately identify in real time, furthermore, it is possible to require identification to carry out weight assignment.
Identification generallys use the broadcasting content in watermark identification or playing platform broadcasting content in real time.
It accurately identifies in the broadcasting generallyd use in watermark identification and fingerprint recognition and combination playing platform broadcasting content
Hold.
For example, watermark can be allowed to identify when the result of watermark identification and the conventional behavior of user have dramatically different
The identification that tries again, which is done, to be confirmed.
For another example, if platform play program arrangement may Iterim Change or fingerprint recognition be also possible to go out
Mistake, playing platform announce played data and fingerprint recognition it is different, then can require fingerprint recognition try again identification etc..
The preset content identification operation includes at least: crosscheck or error correction verifying.
Crosscheck refers to according to the broadcasting content in the first identification request first preference broadcasting content of identification.
Error correction verifying refer to according to it is described first identification request identification the first video and audio broadcasting content in watermark label or
Person's fingerprint label.
In above-mentioned steps, the requirements selection such as real-time, accuracy for being requested according to identification recognition methods appropriate is simultaneously real
Recognition result is exported after existing cross validation, error correction, completes the function of broadcasting content identification service.
Such as table 1
|
Dependence |
High-precision synchronization |
Universality |
Watermark identification |
It needs to pre-process content |
Second grade is synchronous |
It is good |
Fingerprint recognition |
Need to collect all possible program fingerprint characteristics |
At least more than ten seconds |
It is good |
Playing platform provides |
Need platform development interface |
Second grade is synchronous |
It is bad |
User provides |
User provides |
It can not precisely synchronize |
It is good |
Analyze user behavior habit |
User behavior data |
It can not precisely synchronize |
It is good |
The method that these types realizes content recognition as shown in Table 1 is suitable for different scenes.For example, synchronous answer needs make
It is identified with watermark or is formed with platform and cooperated, fingerprint recognition etc. can be used in general content push.Another aspect, this
The integration technology of a little methods can guarantee the validity and universality of content service.For example user provides some specific program,
Or the analysis of user behavior habit can be with the result of cross validation watermark identification and fingerprint recognition;Fingerprint recognition can be with auxiliary water
Print identification first carries out the identification of low precision, to reduce the length etc. of fingerprint recognition code.Therefore, content identification service is using a variety of
The method of technological incorporation, for different application scenarios, the recognition effect that can be optimal.
Figure 11 is please referred to, specifically, when an identification is requested to be come, three kinds of recognition methods operate simultaneously.
First first checks whether the audio/video information that can be collected, if it can, being divided into two parts.First part checks
It is no to have watermark information, then start watermark identification;Second part enters fingerprint recognition, if the requirement of real-time of current identification request
It can be met by fingerprint recognition, then start fingerprint recognition.Second is directly entered user behavior habit analysis prediction engine, this
Recognition result is mainly used to cross-check.Third checks whether user actively provides the information currently watched or listened to,
It is straight if there is entering playing platform data collection engine, the program broadcasting situation of engine collection playing platform, such as TV station
The case where broadcasting program.It is worth noting that if the case where directly cooperating with playing platform, user's request program can be obtained.Most
The result that different recognition methods obtain afterwards enters fusion recognition module, real-time, essence of the fusion recognition module according to identification request
The requirements such as true property select recognition methods appropriate and realize that cross validation, error correction export recognition result later, complete to be based on playing
The function of content recognition.
Obviously, those skilled in the art should be understood that each module of above-mentioned the application or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
Be performed by computing device in the storage device, perhaps they are fabricated to each integrated circuit modules or by they
In multiple modules or step be fabricated to single integrated circuit module to realize.In this way, the application be not limited to it is any specific
Hardware and software combines.
The foregoing is merely preferred embodiment of the present application, are not intended to limit this application, for the skill of this field
For art personnel, various changes and changes are possible in this application.Within the spirit and principles of this application, made any to repair
Change, equivalent replacement, improvement etc., should be included within the scope of protection of this application.